hadasor/Qwen2.5-14B-Instruct-Pruned

TEXT GENERATIONConcurrency Cost:1Model Size:14.8BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 19, 2026Architecture:Transformer Cold

hadasor/Qwen2.5-14B-Instruct-Pruned is a 14.8 billion parameter instruction-tuned language model based on the Qwen2.5 architecture. This model is a pruned version, suggesting optimizations for efficiency or specific task performance. Its instruction-tuned nature indicates it is designed for following commands and generating responses in a conversational or task-oriented manner, making it suitable for general-purpose AI applications requiring instruction adherence.

Loading preview...

Model Overview

hadasor/Qwen2.5-14B-Instruct-Pruned is an instruction-tuned language model with 14.8 billion parameters, built upon the Qwen2.5 architecture. This model is a 'pruned' variant, implying it has undergone optimization to reduce its size or computational requirements while aiming to retain strong performance.

Key Characteristics

  • Architecture: Based on the Qwen2.5 family of models.
  • Parameter Count: 14.8 billion parameters, offering a balance between capability and resource usage.
  • Instruction-Tuned: Designed to understand and follow instructions effectively, making it versatile for various NLP tasks.
  • Pruned Version: Indicates potential optimizations for efficiency, faster inference, or deployment in resource-constrained environments.

Potential Use Cases

  • General-purpose instruction following: Answering questions, summarizing text, generating creative content, and engaging in dialogue based on explicit instructions.
  • Application integration: Suitable for developers looking for a capable instruction-tuned model that might offer performance benefits due to its pruned nature.
  • Research and experimentation: A solid base for further fine-tuning or exploring the impact of pruning on large language models.